unified-deliverable-workflow

Generate spreadsheets, diagrams, and PDF reports with iteration budgeting and error recovery

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/pdf-checklist-workflow-enhanced-780c5d/SKILL.md

Quality

Content

66%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill excels at actionability and workflow clarity with executable code and strong validation feedback loops, but is hurt by verbosity/redundancy and a monolithic structure that violates progressive disclosure. Splitting the large code examples into reference files and trimming duplication would materially raise both weak dimensions.

Suggestions

Move the three full phase code examples into separate files under references/ (e.g. spreadsheet.py, diagram.py, pdf.py) and keep only concise snippets plus links in SKILL.md.

Remove the redundant 'Quick Start Template' or fold it into the phase sections, and consolidate the repeated /workspace/ path guidance into one 'Path Standardization' statement.

Trim the duplicated error-recovery tables by merging per-phase recovery actions into the single 'Error Handling Strategy' list.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the 'Quick Start Template' duplicates the three phase code blocks, error-recovery tables and path warnings repeat across sections, and the /workspace/ path rule is stated 4+ times; several padded/redundant sections could be trimmed.	2 / 5
Actionability	Fully executable copy-paste Python for spreadsheets, diagrams, and PDFs with real library calls, save paths, and ARTIFACT_PATH prints; the Quick Start template is runnable and covers the common cases.	5 / 5
Workflow Clarity	Clear phased sequence (Pre-Flight, Phases 1-3, Phase 4 validation) with per-phase iteration budgets, validation checklists, error-recovery tables, and explicit feedback loops ('If 2 consecutive failures: Skip to Phase 2'), matching the top anchor for batch operations.	5 / 5
Progressive Disclosure	Monolithic ~450-line SKILL.md with no bundle files or references/ directory; three large code blocks that clearly belong in separate reference files are inlined, giving minimal structure with buried, unsignaled references.	2 / 5
	Total	14 / 20 Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description conveys concrete capabilities and a recognizable niche but lacks an explicit 'Use when...' trigger, which caps its completeness. It is solid but stops short of the top anchor on every dimension.

Suggestions

Add an explicit trigger clause, e.g. 'Use when generating multiple related deliverables (Excel spreadsheets, PNG diagrams, PDF reports) in one task'.

Include natural synonyms and file extensions users say (Excel/.xlsx, charts, .png, .pdf) to improve trigger term coverage.

Tighten specificity by naming the generation mechanism (e.g. 'generate via Python in execute_code_sandbox') to approach comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Lists three concrete deliverable types ('spreadsheets, diagrams, and PDF reports') plus two process features ('iteration budgeting and error recovery'); not quite comprehensive since it omits how each is produced, so it sits between anchors 3 and 5, noticeably above the midpoint.	4 / 5
Completeness	Provides a clear 'what' (generate the three artifact types with budgeting and recovery) but has no 'Use when...' trigger clause; per the guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms 'spreadsheets', 'diagrams', 'PDF reports' but omits common synonyms and extensions users say (Excel/.xlsx, charts, .png, .pdf), leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The multi-deliverable bundle niche is mostly distinct, with only minor overlap risk against single-artifact skills (e.g. a PDF-only or diagram-only skill).	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/pdf-checklist-workflow-enhanced-780c5d/SKILL.md
Commit: 3827781

Reviewed: 15 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.